alt text alt text

Data Scientist Nanodegree

Supervised Learning

Project: Build an image classifier

by: Almutairi, Muhanned

alt textLinkedIn profile

Your First AI application

Going forward, AI algorithms will be incorporated into more and more everyday applications. For example, you might want to include an image classifier in a smart phone app. To do this, you'd use a deep learning model trained on hundreds of thousands of images as part of the overall application architecture. A large part of software development in the future will be using these types of models as common parts of applications.

In this project, you'll train an image classifier to recognize different species of flowers. You can imagine using something like this in a phone app that tells you the name of the flower your camera is looking at. In practice you'd train this classifier, then export it for use in your application. We'll be using this dataset from Oxford of 102 flower categories, you can see a few examples below.

The project is broken down into multiple steps:

  • Load the image dataset and create a pipeline.
  • Build and Train an image classifier on this dataset.
  • Use your trained model to perform inference on flower images.

We'll lead you through each part which you'll implement in Python.

When you've completed this project, you'll have an application that can be trained on any set of labeled images. Here your network will be learning about flowers and end up as a command line application. But, what you do with your new skills depends on your imagination and effort in building a dataset. For example, imagine an app where you take a picture of a car, it tells you what the make and model is, then looks up information about it. Go build your own dataset and make something new.

Import Resources

In [1]:
# The new version of dataset is only available in the tfds-nightly package.
%pip --no-cache-dir install tensorflow-datasets --user
# DON'T MISS TO RESTART THE KERNEL
Requirement already satisfied: tensorflow-datasets in /usr/local/lib/python3.6/dist-packages (2.1.0)
Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (2.23.0)
Requirement already satisfied: termcolor in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (1.1.0)
Requirement already satisfied: promise in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (2.3)
Requirement already satisfied: future in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (0.16.0)
Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (1.18.5)
Requirement already satisfied: protobuf>=3.6.1 in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (3.12.4)
Requirement already satisfied: attrs>=18.1.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (20.2.0)
Requirement already satisfied: wrapt in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (1.12.1)
Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (1.15.0)
Requirement already satisfied: tensorflow-metadata in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (0.24.0)
Requirement already satisfied: dill in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (0.3.2)
Requirement already satisfied: tqdm in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (4.41.1)
Requirement already satisfied: absl-py in /usr/local/lib/python3.6/dist-packages (from tensorflow-datasets) (0.10.0)
Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->tensorflow-datasets) (2.10)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->tensorflow-datasets) (2020.6.20)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->tensorflow-datasets) (1.24.3)
Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests>=2.19.0->tensorflow-datasets) (3.0.4)
Requirement already satisfied: setuptools in /usr/local/lib/python3.6/dist-packages (from protobuf>=3.6.1->tensorflow-datasets) (50.3.0)
Requirement already satisfied: googleapis-common-protos<2,>=1.52.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow-metadata->tensorflow-datasets) (1.52.0)
In [2]:
# Import TensorFlow 
import tensorflow as tf
import tensorflow_datasets as tfds
import tensorflow_hub as hub
In [3]:
# TODO: Make all other necessary imports.
%matplotlib inline
%config InlineBackend.figure_format = 'retina'

import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
In [4]:
import logging
logger = tf.get_logger()
logger.setLevel(logging.ERROR)
In [5]:
import warnings
warnings.filterwarnings('ignore')
tfds.disable_progress_bar()
import time
import json
In [6]:
print('Using:')
print('\t\u2022 TensorFlow version:', tf.__version__)
print('\t\u2022 tf.keras version:', tf.keras.__version__)
print('\t\u2022 Running on GPU' if tf.test.is_gpu_available() else '\t\u2022 GPU device not found. Running on CPU')
Using:
	• TensorFlow version: 2.3.0
	• tf.keras version: 2.4.0
	• Running on GPU

Load the Dataset

Here you'll use tensorflow_datasets to load the Oxford Flowers 102 dataset. This dataset has 3 splits: 'train', 'test', and 'validation'. You'll also need to make sure the training data is normalized and resized to 224x224 pixels as required by the pre-trained networks.

The validation and testing sets are used to measure the model's performance on data it hasn't seen yet, but you'll still need to normalize and resize the images to the appropriate size.

In [7]:
# Download data to default local directory "~/tensorflow_datasets"
!python -m tensorflow_datasets.scripts.download_and_prepare --register_checksums=True --datasets=oxford_flowers102

# TODO: Load the dataset with TensorFlow Datasets. Hint: use tfds.load()
dataset, dataset_info = tfds.load('oxford_flowers102', as_supervised=True, with_info=True)
# TODO: Create a training set, a validation set and a test set.
training_set, validation_set, test_set = dataset['train'],dataset['validation'], dataset['test']
2020-10-20 19:49:35.049210: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
I1020 19:49:36.811408 140610746677120 download_and_prepare.py:180] Running download_and_prepare for datasets:
oxford_flowers102
I1020 19:49:36.812080 140610746677120 download_and_prepare.py:181] Version: "None"
I1020 19:49:36.812754 140610746677120 dataset_builder.py:202] Load pre-computed datasetinfo (eg: splits) from bucket.
I1020 19:49:36.884845 140610746677120 dataset_info.py:431] Loading info from GCS for oxford_flowers102/2.0.0
I1020 19:49:37.260588 140610746677120 dataset_info.py:403] Field info.description from disk and from code do not match. Keeping the one from code.
I1020 19:49:37.261129 140610746677120 download_and_prepare.py:130] download_and_prepare for dataset oxford_flowers102/2.0.0...
I1020 19:49:37.261535 140610746677120 dataset_builder.py:310] Generating dataset oxford_flowers102 (/root/tensorflow_datasets/oxford_flowers102/2.0.0)
Downloading and preparing dataset oxford_flowers102/2.0.0 (download: 336.76 MiB, generated: Unknown size, total: 336.76 MiB) to /root/tensorflow_datasets/oxford_flowers102/2.0.0...
Dl Completed...: 0 url [00:00, ? url/s]
Dl Size...: 0 MiB [00:00, ? MiB/s]

Extraction completed...: 0 file [00:00, ? file/s]I1020 19:49:37.418906 140610746677120 download_manager.py:256] Downloading https://www.robots.ox.ac.uk/~vgg/data/flowers/102/102flowers.tgz into /root/tensorflow_datasets/downloads/robots.ox.ac.uk_vgg_flowers_102_102flowersoWedSp98maBn1wypsDib6T-q2NVbO40fwvTflmPmQpY.tgz.tmp.407865f2e9f249c289e933ee20083154...
Dl Completed...:   0% 0/1 [00:00<?, ? url/s]
Dl Size...: 0 MiB [00:00, ? MiB/s]

Extraction completed...: 0 file [00:00, ? file/s]I1020 19:49:37.422109 140610746677120 download_manager.py:256] Downloading https://www.robots.ox.ac.uk/~vgg/data/flowers/102/imagelabels.mat into /root/tensorflow_datasets/downloads/robots.ox.ac.uk_vgg_flowers_102_imagelabelQc558tX8AD-RkJuVyV4EyAI3B3yv3pQFw82vzoHJBkI.mat.tmp.1736f5133e284bacb073fa4dad5b6f5b...
Dl Completed...:   0% 0/2 [00:00<?, ? url/s]
Dl Size...: 0 MiB [00:00, ? MiB/s]

Extraction completed...: 0 file [00:00, ? file/s]I1020 19:49:37.425071 140610746677120 download_manager.py:256] Downloading https://www.robots.ox.ac.uk/~vgg/data/flowers/102/setid.mat into /root/tensorflow_datasets/downloads/robots.ox.ac.uk_vgg_flowers_102_setidSMkjURnWabtzYOtl4t1kAcvHb6vlLbDJOlQsTHUux60.mat.tmp.8b99d3af2291425cb95dcf4477f2426b...
Dl Completed...:   0% 0/3 [00:00<?, ? url/s]
Dl Size...: 0 MiB [00:00, ? MiB/s]

Extraction completed...: 0 file [00:00, ? file/s]/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
  InsecureRequestWarning)
/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
  InsecureRequestWarning)
/usr/local/lib/python3.6/dist-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
  InsecureRequestWarning)
Dl Completed...:   0% 0/3 [00:00<?, ? url/s]
Dl Size...:   0% 0/328 [00:00<?, ? MiB/s]

Dl Completed...:   0% 0/3 [00:00<?, ? url/s]
Dl Size...:   0% 0/328 [00:00<?, ? MiB/s]

Dl Completed...:  33% 1/3 [00:00<00:01,  1.48 url/s]
Dl Size...:   0% 0/328 [00:00<?, ? MiB/s]

Extraction completed...: 0 file [00:00, ? file/s]I1020 19:49:38.096906 140609496905472 download_manager.py:273] Skipping extraction for /root/tensorflow_datasets/downloads/robots.ox.ac.uk_vgg_flowers_102_imagelabelSQPpQga6wjv3cqrfBkUZFt9WtY_Eg6YtsyqXuCZWZR0.mat (method=NO_EXTRACT).
Dl Completed...:  33% 1/3 [00:00<00:01,  1.48 url/s]
Dl Size...:   0% 0/328 [00:00<?, ? MiB/s]

Dl Completed...:  67% 2/3 [00:00<00:00,  1.93 url/s]
Dl Size...:   0% 0/328 [00:00<?, ? MiB/s]

Extraction completed...: 0 file [00:00, ? file/s]I1020 19:49:38.242879 140609488512768 download_manager.py:273] Skipping extraction for /root/tensorflow_datasets/downloads/robots.ox.ac.uk_vgg_flowers_102_setidRrhnj5H9ldPI9P6rgNJxpsg0od2Jb-Kf0-atnOXI3M0.mat (method=NO_EXTRACT).

Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   0% 1/328 [00:01<07:56,  1.46s/ MiB]

Extraction completed...: 0 file [00:01, ? file/s]
Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   1% 2/328 [00:01<05:45,  1.06s/ MiB]

Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   1% 3/328 [00:01<05:44,  1.06s/ MiB]

Extraction completed...: 0 file [00:01, ? file/s]
Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   1% 4/328 [00:01<04:06,  1.31 MiB/s]

Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   2% 5/328 [00:01<04:06,  1.31 MiB/s]

Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   2% 6/328 [00:01<04:05,  1.31 MiB/s]

Extraction completed...: 0 file [00:01, ? file/s]
Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   2% 7/328 [00:01<02:55,  1.83 MiB/s]

Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   2% 8/328 [00:01<02:54,  1.83 MiB/s]

Extraction completed...: 0 file [00:01, ? file/s]
Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   3% 9/328 [00:01<02:07,  2.49 MiB/s]

Dl Completed...:  67% 2/3 [00:01<00:00,  1.93 url/s]
Dl Size...:   3% 10/328 [00:01<02:07,  2.49 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   3% 11/328 [00:02<02:07,  2.49 MiB/s]

Extraction completed...: 0 file [00:02, ? file/s]
Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   4% 12/328 [00:02<01:32,  3.40 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   4% 13/328 [00:02<01:32,  3.40 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   4% 14/328 [00:02<01:32,  3.40 MiB/s]

Extraction completed...: 0 file [00:02, ? file/s]
Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   5% 15/328 [00:02<01:08,  4.57 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   5% 16/328 [00:02<01:08,  4.57 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   5% 17/328 [00:02<01:08,  4.57 MiB/s]

Extraction completed...: 0 file [00:02, ? file/s]
Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   5% 18/328 [00:02<00:51,  6.01 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   6% 19/328 [00:02<00:51,  6.01 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   6% 20/328 [00:02<00:51,  6.01 MiB/s]

Extraction completed...: 0 file [00:02, ? file/s]
Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   6% 21/328 [00:02<00:40,  7.62 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   7% 22/328 [00:02<00:40,  7.62 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   7% 23/328 [00:02<00:40,  7.62 MiB/s]

Extraction completed...: 0 file [00:02, ? file/s]
Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   7% 24/328 [00:02<00:31,  9.52 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   8% 25/328 [00:02<00:31,  9.52 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   8% 26/328 [00:02<00:31,  9.52 MiB/s]

Extraction completed...: 0 file [00:02, ? file/s]
Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   8% 27/328 [00:02<00:26, 11.34 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   9% 28/328 [00:02<00:26, 11.34 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   9% 29/328 [00:02<00:26, 11.34 MiB/s]

Extraction completed...: 0 file [00:02, ? file/s]
Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   9% 30/328 [00:02<00:22, 13.28 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:   9% 31/328 [00:02<00:22, 13.28 MiB/s]

Dl Completed...:  67% 2/3 [00:02<00:00,  1.93 url/s]
Dl Size...:  10% 32/328 [00:02<00:22, 13.28 MiB/s]

Extraction completed...: 0 file [00:02, ? file/s]
Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  10% 33/328 [00:03<00:19, 15.07 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  10% 34/328 [00:03<00:19, 15.07 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  11% 35/328 [00:03<00:19, 15.07 MiB/s]

Extraction completed...: 0 file [00:03, ? file/s]
Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  11% 36/328 [00:03<00:17, 16.59 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  11% 37/328 [00:03<00:17, 16.59 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  12% 38/328 [00:03<00:17, 16.59 MiB/s]

Extraction completed...: 0 file [00:03, ? file/s]
Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  12% 39/328 [00:03<00:16, 17.88 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  12% 40/328 [00:03<00:16, 17.88 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  12% 41/328 [00:03<00:16, 17.88 MiB/s]

Extraction completed...: 0 file [00:03, ? file/s]
Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  13% 42/328 [00:03<00:15, 18.89 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  13% 43/328 [00:03<00:15, 18.89 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  13% 44/328 [00:03<00:15, 18.89 MiB/s]

Extraction completed...: 0 file [00:03, ? file/s]
Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  14% 45/328 [00:03<00:14, 19.60 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  14% 46/328 [00:03<00:14, 19.60 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  14% 47/328 [00:03<00:14, 19.60 MiB/s]

Extraction completed...: 0 file [00:03, ? file/s]
Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  15% 48/328 [00:03<00:13, 20.34 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  15% 49/328 [00:03<00:13, 20.34 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  15% 50/328 [00:03<00:13, 20.34 MiB/s]

Extraction completed...: 0 file [00:03, ? file/s]
Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  16% 51/328 [00:03<00:13, 20.76 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  16% 52/328 [00:03<00:13, 20.76 MiB/s]

Dl Completed...:  67% 2/3 [00:03<00:00,  1.93 url/s]
Dl Size...:  16% 53/328 [00:03<00:13, 20.76 MiB/s]

Extraction completed...: 0 file [00:03, ? file/s]
Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  16% 54/328 [00:04<00:13, 21.03 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  17% 55/328 [00:04<00:12, 21.03 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  17% 56/328 [00:04<00:12, 21.03 MiB/s]

Extraction completed...: 0 file [00:04, ? file/s]
Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  17% 57/328 [00:04<00:12, 21.34 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  18% 58/328 [00:04<00:12, 21.34 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  18% 59/328 [00:04<00:12, 21.34 MiB/s]

Extraction completed...: 0 file [00:04, ? file/s]
Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  18% 60/328 [00:04<00:12, 21.49 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  19% 61/328 [00:04<00:12, 21.49 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  19% 62/328 [00:04<00:12, 21.49 MiB/s]

Extraction completed...: 0 file [00:04, ? file/s]
Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  19% 63/328 [00:04<00:12, 21.56 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  20% 64/328 [00:04<00:12, 21.56 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  20% 65/328 [00:04<00:12, 21.56 MiB/s]

Extraction completed...: 0 file [00:04, ? file/s]
Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  20% 66/328 [00:04<00:12, 21.62 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  20% 67/328 [00:04<00:12, 21.62 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  21% 68/328 [00:04<00:12, 21.62 MiB/s]

Extraction completed...: 0 file [00:04, ? file/s]
Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  21% 69/328 [00:04<00:11, 21.67 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  21% 70/328 [00:04<00:11, 21.67 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  22% 71/328 [00:04<00:11, 21.67 MiB/s]

Extraction completed...: 0 file [00:04, ? file/s]
Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  22% 72/328 [00:04<00:11, 21.71 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  22% 73/328 [00:04<00:11, 21.71 MiB/s]

Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  23% 74/328 [00:04<00:11, 21.71 MiB/s]

Extraction completed...: 0 file [00:04, ? file/s]
Dl Completed...:  67% 2/3 [00:04<00:00,  1.93 url/s]
Dl Size...:  23% 75/328 [00:04<00:11, 21.71 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  23% 76/328 [00:05<00:11, 21.71 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  23% 77/328 [00:05<00:11, 21.71 MiB/s]

Extraction completed...: 0 file [00:05, ? file/s]
Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  24% 78/328 [00:05<00:11, 21.70 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  24% 79/328 [00:05<00:11, 21.70 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  24% 80/328 [00:05<00:11, 21.70 MiB/s]

Extraction completed...: 0 file [00:05, ? file/s]
Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  25% 81/328 [00:05<00:11, 21.74 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  25% 82/328 [00:05<00:11, 21.74 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  25% 83/328 [00:05<00:11, 21.74 MiB/s]

Extraction completed...: 0 file [00:05, ? file/s]
Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  26% 84/328 [00:05<00:11, 21.74 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  26% 85/328 [00:05<00:11, 21.74 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  26% 86/328 [00:05<00:11, 21.74 MiB/s]

Extraction completed...: 0 file [00:05, ? file/s]
Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  27% 87/328 [00:05<00:11, 21.73 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  27% 88/328 [00:05<00:11, 21.73 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  27% 89/328 [00:05<00:10, 21.73 MiB/s]

Extraction completed...: 0 file [00:05, ? file/s]
Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  27% 90/328 [00:05<00:10, 21.79 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  28% 91/328 [00:05<00:10, 21.79 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  28% 92/328 [00:05<00:10, 21.79 MiB/s]

Extraction completed...: 0 file [00:05, ? file/s]
Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  28% 93/328 [00:05<00:10, 21.76 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  29% 94/328 [00:05<00:10, 21.76 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  29% 95/328 [00:05<00:10, 21.76 MiB/s]

Extraction completed...: 0 file [00:05, ? file/s]
Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  29% 96/328 [00:05<00:10, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:05<00:00,  1.93 url/s]
Dl Size...:  30% 97/328 [00:05<00:10, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  30% 98/328 [00:06<00:10, 21.85 MiB/s]

Extraction completed...: 0 file [00:06, ? file/s]
Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  30% 99/328 [00:06<00:10, 21.79 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  30% 100/328 [00:06<00:10, 21.79 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  31% 101/328 [00:06<00:10, 21.79 MiB/s]

Extraction completed...: 0 file [00:06, ? file/s]
Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  31% 102/328 [00:06<00:10, 21.77 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  31% 103/328 [00:06<00:10, 21.77 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  32% 104/328 [00:06<00:10, 21.77 MiB/s]

Extraction completed...: 0 file [00:06, ? file/s]
Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  32% 105/328 [00:06<00:10, 21.91 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  32% 106/328 [00:06<00:10, 21.91 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  33% 107/328 [00:06<00:10, 21.91 MiB/s]

Extraction completed...: 0 file [00:06, ? file/s]
Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  33% 108/328 [00:06<00:10, 21.84 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  33% 109/328 [00:06<00:10, 21.84 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  34% 110/328 [00:06<00:09, 21.84 MiB/s]

Extraction completed...: 0 file [00:06, ? file/s]
Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  34% 111/328 [00:06<00:09, 21.73 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  34% 112/328 [00:06<00:09, 21.73 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  34% 113/328 [00:06<00:09, 21.73 MiB/s]

Extraction completed...: 0 file [00:06, ? file/s]
Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  35% 114/328 [00:06<00:09, 21.55 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  35% 115/328 [00:06<00:09, 21.55 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  35% 116/328 [00:06<00:09, 21.55 MiB/s]

Extraction completed...: 0 file [00:06, ? file/s]
Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  36% 117/328 [00:06<00:09, 21.88 MiB/s]

Dl Completed...:  67% 2/3 [00:06<00:00,  1.93 url/s]
Dl Size...:  36% 118/328 [00:06<00:09, 21.88 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  36% 119/328 [00:07<00:09, 21.88 MiB/s]

Extraction completed...: 0 file [00:07, ? file/s]
Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  37% 120/328 [00:07<00:09, 21.56 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  37% 121/328 [00:07<00:09, 21.56 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  37% 122/328 [00:07<00:09, 21.56 MiB/s]

Extraction completed...: 0 file [00:07, ? file/s]
Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  38% 123/328 [00:07<00:09, 21.96 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  38% 124/328 [00:07<00:09, 21.96 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  38% 125/328 [00:07<00:09, 21.96 MiB/s]

Extraction completed...: 0 file [00:07, ? file/s]
Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  38% 126/328 [00:07<00:09, 21.84 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  39% 127/328 [00:07<00:09, 21.84 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  39% 128/328 [00:07<00:09, 21.84 MiB/s]

Extraction completed...: 0 file [00:07, ? file/s]
Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  39% 129/328 [00:07<00:09, 21.81 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  40% 130/328 [00:07<00:09, 21.81 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  40% 131/328 [00:07<00:09, 21.81 MiB/s]

Extraction completed...: 0 file [00:07, ? file/s]
Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  40% 132/328 [00:07<00:08, 21.82 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  41% 133/328 [00:07<00:08, 21.82 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  41% 134/328 [00:07<00:08, 21.82 MiB/s]

Extraction completed...: 0 file [00:07, ? file/s]
Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  41% 135/328 [00:07<00:08, 21.83 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  41% 136/328 [00:07<00:08, 21.83 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  42% 137/328 [00:07<00:08, 21.83 MiB/s]

Extraction completed...: 0 file [00:07, ? file/s]
Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  42% 138/328 [00:07<00:08, 21.92 MiB/s]

Dl Completed...:  67% 2/3 [00:07<00:00,  1.93 url/s]
Dl Size...:  42% 139/328 [00:07<00:08, 21.92 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  43% 140/328 [00:08<00:08, 21.92 MiB/s]

Extraction completed...: 0 file [00:08, ? file/s]
Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  43% 141/328 [00:08<00:08, 21.89 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  43% 142/328 [00:08<00:08, 21.89 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  44% 143/328 [00:08<00:08, 21.89 MiB/s]

Extraction completed...: 0 file [00:08, ? file/s]
Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  44% 144/328 [00:08<00:08, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  44% 145/328 [00:08<00:08, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  45% 146/328 [00:08<00:08, 21.75 MiB/s]

Extraction completed...: 0 file [00:08, ? file/s]
Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  45% 147/328 [00:08<00:08, 21.82 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  45% 148/328 [00:08<00:08, 21.82 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  45% 149/328 [00:08<00:08, 21.82 MiB/s]

Extraction completed...: 0 file [00:08, ? file/s]
Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  46% 150/328 [00:08<00:08, 21.80 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  46% 151/328 [00:08<00:08, 21.80 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  46% 152/328 [00:08<00:08, 21.80 MiB/s]

Extraction completed...: 0 file [00:08, ? file/s]
Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  47% 153/328 [00:08<00:08, 21.70 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  47% 154/328 [00:08<00:08, 21.70 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  47% 155/328 [00:08<00:07, 21.70 MiB/s]

Extraction completed...: 0 file [00:08, ? file/s]
Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  48% 156/328 [00:08<00:07, 21.81 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  48% 157/328 [00:08<00:07, 21.81 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  48% 158/328 [00:08<00:07, 21.81 MiB/s]

Extraction completed...: 0 file [00:08, ? file/s]
Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  48% 159/328 [00:08<00:07, 21.70 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  49% 160/328 [00:08<00:07, 21.70 MiB/s]

Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  49% 161/328 [00:08<00:07, 21.70 MiB/s]

Extraction completed...: 0 file [00:08, ? file/s]
Dl Completed...:  67% 2/3 [00:08<00:00,  1.93 url/s]
Dl Size...:  49% 162/328 [00:08<00:07, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  50% 163/328 [00:09<00:07, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  50% 164/328 [00:09<00:07, 21.85 MiB/s]

Extraction completed...: 0 file [00:09, ? file/s]
Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  50% 165/328 [00:09<00:07, 21.82 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  51% 166/328 [00:09<00:07, 21.82 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  51% 167/328 [00:09<00:07, 21.82 MiB/s]

Extraction completed...: 0 file [00:09, ? file/s]
Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  51% 168/328 [00:09<00:07, 21.74 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  52% 169/328 [00:09<00:07, 21.74 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  52% 170/328 [00:09<00:07, 21.74 MiB/s]

Extraction completed...: 0 file [00:09, ? file/s]
Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  52% 171/328 [00:09<00:07, 21.86 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  52% 172/328 [00:09<00:07, 21.86 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  53% 173/328 [00:09<00:07, 21.86 MiB/s]

Extraction completed...: 0 file [00:09, ? file/s]
Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  53% 174/328 [00:09<00:07, 21.81 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  53% 175/328 [00:09<00:07, 21.81 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  54% 176/328 [00:09<00:06, 21.81 MiB/s]

Extraction completed...: 0 file [00:09, ? file/s]
Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  54% 177/328 [00:09<00:06, 21.69 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  54% 178/328 [00:09<00:06, 21.69 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  55% 179/328 [00:09<00:06, 21.69 MiB/s]

Extraction completed...: 0 file [00:09, ? file/s]
Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  55% 180/328 [00:09<00:06, 21.76 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  55% 181/328 [00:09<00:06, 21.76 MiB/s]

Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  55% 182/328 [00:09<00:06, 21.76 MiB/s]

Extraction completed...: 0 file [00:09, ? file/s]
Dl Completed...:  67% 2/3 [00:09<00:00,  1.93 url/s]
Dl Size...:  56% 183/328 [00:09<00:06, 21.78 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  56% 184/328 [00:10<00:06, 21.78 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  56% 185/328 [00:10<00:06, 21.78 MiB/s]

Extraction completed...: 0 file [00:10, ? file/s]
Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  57% 186/328 [00:10<00:06, 21.72 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  57% 187/328 [00:10<00:06, 21.72 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  57% 188/328 [00:10<00:06, 21.72 MiB/s]

Extraction completed...: 0 file [00:10, ? file/s]
Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  58% 189/328 [00:10<00:06, 21.82 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  58% 190/328 [00:10<00:06, 21.82 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  58% 191/328 [00:10<00:06, 21.82 MiB/s]

Extraction completed...: 0 file [00:10, ? file/s]
Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  59% 192/328 [00:10<00:06, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  59% 193/328 [00:10<00:06, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  59% 194/328 [00:10<00:06, 21.85 MiB/s]

Extraction completed...: 0 file [00:10, ? file/s]
Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  59% 195/328 [00:10<00:06, 21.69 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  60% 196/328 [00:10<00:06, 21.69 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  60% 197/328 [00:10<00:06, 21.69 MiB/s]

Extraction completed...: 0 file [00:10, ? file/s]
Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  60% 198/328 [00:10<00:05, 21.89 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  61% 199/328 [00:10<00:05, 21.89 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  61% 200/328 [00:10<00:05, 21.89 MiB/s]

Extraction completed...: 0 file [00:10, ? file/s]
Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  61% 201/328 [00:10<00:05, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  62% 202/328 [00:10<00:05, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  62% 203/328 [00:10<00:05, 21.85 MiB/s]

Extraction completed...: 0 file [00:10, ? file/s]
Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  62% 204/328 [00:10<00:05, 21.86 MiB/s]

Dl Completed...:  67% 2/3 [00:10<00:00,  1.93 url/s]
Dl Size...:  62% 205/328 [00:10<00:05, 21.86 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  63% 206/328 [00:11<00:05, 21.86 MiB/s]

Extraction completed...: 0 file [00:11, ? file/s]
Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  63% 207/328 [00:11<00:05, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  63% 208/328 [00:11<00:05, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  64% 209/328 [00:11<00:05, 21.75 MiB/s]

Extraction completed...: 0 file [00:11, ? file/s]
Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  64% 210/328 [00:11<00:05, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  64% 211/328 [00:11<00:05, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  65% 212/328 [00:11<00:05, 21.75 MiB/s]

Extraction completed...: 0 file [00:11, ? file/s]
Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  65% 213/328 [00:11<00:05, 21.78 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  65% 214/328 [00:11<00:05, 21.78 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  66% 215/328 [00:11<00:05, 21.78 MiB/s]

Extraction completed...: 0 file [00:11, ? file/s]
Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  66% 216/328 [00:11<00:05, 21.61 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  66% 217/328 [00:11<00:05, 21.61 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  66% 218/328 [00:11<00:05, 21.61 MiB/s]

Extraction completed...: 0 file [00:11, ? file/s]
Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  67% 219/328 [00:11<00:04, 21.87 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  67% 220/328 [00:11<00:04, 21.87 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  67% 221/328 [00:11<00:04, 21.87 MiB/s]

Extraction completed...: 0 file [00:11, ? file/s]
Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  68% 222/328 [00:11<00:04, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  68% 223/328 [00:11<00:04, 21.85 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  68% 224/328 [00:11<00:04, 21.85 MiB/s]

Extraction completed...: 0 file [00:11, ? file/s]
Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  69% 225/328 [00:11<00:04, 21.41 MiB/s]

Dl Completed...:  67% 2/3 [00:11<00:00,  1.93 url/s]
Dl Size...:  69% 226/328 [00:11<00:04, 21.41 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  69% 227/328 [00:12<00:04, 21.41 MiB/s]

Extraction completed...: 0 file [00:12, ? file/s]
Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  70% 228/328 [00:12<00:04, 21.70 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  70% 229/328 [00:12<00:04, 21.70 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  70% 230/328 [00:12<00:04, 21.70 MiB/s]

Extraction completed...: 0 file [00:12, ? file/s]
Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  70% 231/328 [00:12<00:04, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  71% 232/328 [00:12<00:04, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  71% 233/328 [00:12<00:04, 21.75 MiB/s]

Extraction completed...: 0 file [00:12, ? file/s]
Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  71% 234/328 [00:12<00:04, 21.73 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  72% 235/328 [00:12<00:04, 21.73 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  72% 236/328 [00:12<00:04, 21.73 MiB/s]

Extraction completed...: 0 file [00:12, ? file/s]
Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  72% 237/328 [00:12<00:04, 21.72 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  73% 238/328 [00:12<00:04, 21.72 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  73% 239/328 [00:12<00:04, 21.72 MiB/s]

Extraction completed...: 0 file [00:12, ? file/s]
Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  73% 240/328 [00:12<00:04, 21.71 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  73% 241/328 [00:12<00:04, 21.71 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  74% 242/328 [00:12<00:03, 21.71 MiB/s]

Extraction completed...: 0 file [00:12, ? file/s]
Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  74% 243/328 [00:12<00:03, 21.68 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  74% 244/328 [00:12<00:03, 21.68 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  75% 245/328 [00:12<00:03, 21.68 MiB/s]

Extraction completed...: 0 file [00:12, ? file/s]
Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  75% 246/328 [00:12<00:03, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  75% 247/328 [00:12<00:03, 21.75 MiB/s]

Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  76% 248/328 [00:12<00:03, 21.75 MiB/s]

Extraction completed...: 0 file [00:12, ? file/s]
Dl Completed...:  67% 2/3 [00:12<00:00,  1.93 url/s]
Dl Size...:  76% 249/328 [00:12<00:03, 21.76 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  76% 250/328 [00:13<00:03, 21.76 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  77% 251/328 [00:13<00:03, 21.76 MiB/s]

Extraction completed...: 0 file [00:13, ? file/s]
Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  77% 252/328 [00:13<00:03, 21.69 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  77% 253/328 [00:13<00:03, 21.69 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  77% 254/328 [00:13<00:03, 21.69 MiB/s]

Extraction completed...: 0 file [00:13, ? file/s]
Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  78% 255/328 [00:13<00:03, 21.77 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  78% 256/328 [00:13<00:03, 21.77 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  78% 257/328 [00:13<00:03, 21.77 MiB/s]

Extraction completed...: 0 file [00:13, ? file/s]
Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  79% 258/328 [00:13<00:03, 21.11 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  79% 259/328 [00:13<00:03, 21.11 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  79% 260/328 [00:13<00:03, 21.11 MiB/s]

Extraction completed...: 0 file [00:13, ? file/s]
Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  80% 261/328 [00:13<00:03, 21.32 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  80% 262/328 [00:13<00:03, 21.32 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  80% 263/328 [00:13<00:03, 21.32 MiB/s]

Extraction completed...: 0 file [00:13, ? file/s]
Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  80% 264/328 [00:13<00:02, 21.72 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  81% 265/328 [00:13<00:02, 21.72 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  81% 266/328 [00:13<00:02, 21.72 MiB/s]

Extraction completed...: 0 file [00:13, ? file/s]
Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  81% 267/328 [00:13<00:02, 22.03 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  82% 268/328 [00:13<00:02, 22.03 MiB/s]

Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  82% 269/328 [00:13<00:02, 22.03 MiB/s]

Extraction completed...: 0 file [00:13, ? file/s]
Dl Completed...:  67% 2/3 [00:13<00:00,  1.93 url/s]
Dl Size...:  82% 270/328 [00:13<00:02, 22.19 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  83% 271/328 [00:14<00:02, 22.19 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  83% 272/328 [00:14<00:02, 22.19 MiB/s]

Extraction completed...: 0 file [00:14, ? file/s]
Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  83% 273/328 [00:14<00:02, 22.17 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  84% 274/328 [00:14<00:02, 22.17 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  84% 275/328 [00:14<00:02, 22.17 MiB/s]

Extraction completed...: 0 file [00:14, ? file/s]
Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  84% 276/328 [00:14<00:02, 22.07 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  84% 277/328 [00:14<00:02, 22.07 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  85% 278/328 [00:14<00:02, 22.07 MiB/s]

Extraction completed...: 0 file [00:14, ? file/s]
Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  85% 279/328 [00:14<00:02, 21.96 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  85% 280/328 [00:14<00:02, 21.96 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  86% 281/328 [00:14<00:02, 21.96 MiB/s]

Extraction completed...: 0 file [00:14, ? file/s]
Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  86% 282/328 [00:14<00:02, 21.84 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  86% 283/328 [00:14<00:02, 21.84 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  87% 284/328 [00:14<00:02, 21.84 MiB/s]

Extraction completed...: 0 file [00:14, ? file/s]
Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  87% 285/328 [00:14<00:01, 21.88 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  87% 286/328 [00:14<00:01, 21.88 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  88% 287/328 [00:14<00:01, 21.88 MiB/s]

Extraction completed...: 0 file [00:14, ? file/s]
Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  88% 288/328 [00:14<00:01, 21.89 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  88% 289/328 [00:14<00:01, 21.89 MiB/s]

Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  88% 290/328 [00:14<00:01, 21.89 MiB/s]

Extraction completed...: 0 file [00:14, ? file/s]
Dl Completed...:  67% 2/3 [00:14<00:00,  1.93 url/s]
Dl Size...:  89% 291/328 [00:14<00:01, 21.72 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  89% 292/328 [00:15<00:01, 21.72 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  89% 293/328 [00:15<00:01, 21.72 MiB/s]

Extraction completed...: 0 file [00:15, ? file/s]
Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  90% 294/328 [00:15<00:01, 21.76 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  90% 295/328 [00:15<00:01, 21.76 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  90% 296/328 [00:15<00:01, 21.76 MiB/s]

Extraction completed...: 0 file [00:15, ? file/s]
Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  91% 297/328 [00:15<00:01, 21.84 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  91% 298/328 [00:15<00:01, 21.84 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  91% 299/328 [00:15<00:01, 21.84 MiB/s]

Extraction completed...: 0 file [00:15, ? file/s]
Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  91% 300/328 [00:15<00:01, 20.46 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  92% 301/328 [00:15<00:01, 20.46 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  92% 302/328 [00:15<00:01, 20.46 MiB/s]

Extraction completed...: 0 file [00:15, ? file/s]
Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  92% 303/328 [00:15<00:01, 21.13 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  93% 304/328 [00:15<00:01, 21.13 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  93% 305/328 [00:15<00:01, 21.13 MiB/s]

Extraction completed...: 0 file [00:15, ? file/s]
Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  93% 306/328 [00:15<00:01, 20.75 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  94% 307/328 [00:15<00:01, 20.75 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  94% 308/328 [00:15<00:00, 20.75 MiB/s]

Extraction completed...: 0 file [00:15, ? file/s]
Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  94% 309/328 [00:15<00:00, 21.29 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  95% 310/328 [00:15<00:00, 21.29 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  95% 311/328 [00:15<00:00, 21.29 MiB/s]

Extraction completed...: 0 file [00:15, ? file/s]
Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  95% 312/328 [00:15<00:00, 20.80 MiB/s]

Dl Completed...:  67% 2/3 [00:15<00:00,  1.93 url/s]
Dl Size...:  95% 313/328 [00:15<00:00, 20.80 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  96% 314/328 [00:16<00:00, 20.80 MiB/s]

Extraction completed...: 0 file [00:16, ? file/s]
Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  96% 315/328 [00:16<00:00, 20.87 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  96% 316/328 [00:16<00:00, 20.87 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  97% 317/328 [00:16<00:00, 20.87 MiB/s]

Extraction completed...: 0 file [00:16, ? file/s]
Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  97% 318/328 [00:16<00:00, 21.13 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  97% 319/328 [00:16<00:00, 21.13 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  98% 320/328 [00:16<00:00, 21.13 MiB/s]

Extraction completed...: 0 file [00:16, ? file/s]
Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  98% 321/328 [00:16<00:00, 20.96 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  98% 322/328 [00:16<00:00, 20.96 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  98% 323/328 [00:16<00:00, 20.96 MiB/s]

Extraction completed...: 0 file [00:16, ? file/s]
Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  99% 324/328 [00:16<00:00, 21.48 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  99% 325/328 [00:16<00:00, 21.48 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...:  99% 326/328 [00:16<00:00, 21.48 MiB/s]

Extraction completed...: 0 file [00:16, ? file/s]
Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...: 100% 327/328 [00:16<00:00, 21.60 MiB/s]

Dl Completed...:  67% 2/3 [00:16<00:00,  1.93 url/s]
Dl Size...: 100% 328/328 [00:16<00:00, 21.60 MiB/s]

Dl Completed...: 100% 3/3 [00:16<00:00,  5.12s/ url]
Dl Size...: 100% 328/328 [00:16<00:00, 21.60 MiB/s]

Dl Completed...: 100% 3/3 [00:16<00:00,  5.12s/ url]
Dl Size...: 100% 328/328 [00:16<00:00, 21.60 MiB/s]

Extraction completed...:   0% 0/1 [00:16<?, ? file/s]

Dl Completed...: 100% 3/3 [00:21<00:00,  5.12s/ url]
Dl Size...: 100% 328/328 [00:21<00:00, 21.60 MiB/s]

Extraction completed...: 100% 1/1 [00:21<00:00, 21.33s/ file]
Extraction completed...: 100% 1/1 [00:21<00:00, 21.34s/ file]

Dl Size...: 100% 328/328 [00:21<00:00, 15.37 MiB/s]

Dl Completed...: 100% 3/3 [00:21<00:00,  7.11s/ url]
I1020 19:49:58.753604 140610746677120 dataset_builder.py:927] Generating split train
Shuffling and writing examples to /root/tensorflow_datasets/oxford_flowers102/2.0.0.incomplete37LVX4/oxford_flowers102-train.tfrecord
  0% 0/1020 [00:00<?, ? examples/s]I1020 19:49:59.340180 140610746677120 tfrecords_writer.py:228] Done writing /root/tensorflow_datasets/oxford_flowers102/2.0.0.incomplete37LVX4/oxford_flowers102-train.tfrecord. Shard lengths: [1020]
I1020 19:49:59.346259 140610746677120 dataset_builder.py:927] Generating split test
Shuffling and writing examples to /root/tensorflow_datasets/oxford_flowers102/2.0.0.incomplete37LVX4/oxford_flowers102-test.tfrecord
 85% 5244/6149 [00:00<00:00, 17318.90 examples/s]I1020 19:50:02.795303 140610746677120 tfrecords_writer.py:228] Done writing /root/tensorflow_datasets/oxford_flowers102/2.0.0.incomplete37LVX4/oxford_flowers102-test.tfrecord. Shard lengths: [3074, 3075]
I1020 19:50:02.827461 140610746677120 dataset_builder.py:927] Generating split validation
Shuffling and writing examples to /root/tensorflow_datasets/oxford_flowers102/2.0.0.incomplete37LVX4/oxford_flowers102-validation.tfrecord
  0% 0/1020 [00:00<?, ? examples/s]I1020 19:50:03.379388 140610746677120 tfrecords_writer.py:228] Done writing /root/tensorflow_datasets/oxford_flowers102/2.0.0.incomplete37LVX4/oxford_flowers102-validation.tfrecord. Shard lengths: [1020]
I1020 19:50:03.384299 140610746677120 dataset_builder.py:359] Computing statistics.
Computing statistics...:   0% 0/3 [00:00<?, ? split/s]I1020 19:50:03.384913 140610746677120 dataset_builder.py:458] Constructing tf.data.Dataset for split test, from /root/tensorflow_datasets/oxford_flowers102/2.0.0.incomplete37LVX4
2020-10-20 19:50:03.389676: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1
2020-10-20 19:50:03.392255: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-10-20 19:50:03.392849: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: 
pciBusID: 0000:00:04.0 name: Tesla P100-PCIE-16GB computeCapability: 6.0
coreClock: 1.3285GHz coreCount: 56 deviceMemorySize: 15.90GiB deviceMemoryBandwidth: 681.88GiB/s
2020-10-20 19:50:03.392894: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
2020-10-20 19:50:03.394396: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2020-10-20 19:50:03.395822: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2020-10-20 19:50:03.396150: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2020-10-20 19:50:03.397622: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2020-10-20 19:50:03.398384: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2020-10-20 19:50:03.401505: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7
2020-10-20 19:50:03.401624: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-10-20 19:50:03.402274: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-10-20 19:50:03.402810: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0
2020-10-20 19:50:03.407994: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 2200000000 Hz
2020-10-20 19:50:03.408198: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2d5ebc0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-10-20 19:50:03.408227: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
2020-10-20 19:50:03.499725: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-10-20 19:50:03.500446: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x2d5f480 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2020-10-20 19:50:03.500496: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Tesla P100-PCIE-16GB, Compute Capability 6.0
2020-10-20 19:50:03.500693: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-10-20 19:50:03.501283: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties: 
pciBusID: 0000:00:04.0 name: Tesla P100-PCIE-16GB computeCapability: 6.0
coreClock: 1.3285GHz coreCount: 56 deviceMemorySize: 15.90GiB deviceMemoryBandwidth: 681.88GiB/s
2020-10-20 19:50:03.501341: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
2020-10-20 19:50:03.501383: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcublas.so.10
2020-10-20 19:50:03.501423: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcufft.so.10
2020-10-20 19:50:03.501444: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcurand.so.10
2020-10-20 19:50:03.501463: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusolver.so.10
2020-10-20 19:50:03.501483: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcusparse.so.10
2020-10-20 19:50:03.501505: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudnn.so.7
2020-10-20 19:50:03.501578: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-10-20 19:50:03.502163: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-10-20 19:50:03.502722: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0
2020-10-20 19:50:03.502768: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.1
2020-10-20 19:50:04.055010: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-10-20 19:50:04.055070: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263]      0 
2020-10-20 19:50:04.055083: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1276] 0:   N 
2020-10-20 19:50:04.055281: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-10-20 19:50:04.055943: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:982] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2020-10-20 19:50:04.056486: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:39] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0.
2020-10-20 19:50:04.056529: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1402] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14640 MB memory) -> physical GPU (device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:00:04.0, compute capability: 6.0)

0 examples [00:00, ? examples/s]
1 examples [00:00,  4.11 examples/s]
39 examples [00:00,  5.84 examples/s]
77 examples [00:00,  8.29 examples/s]
112 examples [00:00, 11.72 examples/s]
153 examples [00:00, 16.54 examples/s]
194 examples [00:00, 23.23 examples/s]
227 examples [00:00, 32.20 examples/s]
266 examples [00:00, 44.42 examples/s]
302 examples [00:01, 60.26 examples/s]
337 examples [00:01, 79.94 examples/s]
375 examples [00:01, 104.46 examples/s]
411 examples [00:01, 132.37 examples/s]
449 examples [00:01, 164.07 examples/s]
488 examples [00:01, 198.42 examples/s]
528 examples [00:01, 232.96 examples/s]
568 examples [00:01, 265.71 examples/s]
607 examples [00:01, 292.41 examples/s]
647 examples [00:01, 317.10 examples/s]
686 examples [00:02, 327.27 examples/s]
724 examples [00:02, 336.40 examples/s]
764 examples [00:02, 350.70 examples/s]
804 examples [00:02, 357.48 examples/s]
842 examples [00:02, 354.72 examples/s]
883 examples [00:02, 369.51 examples/s]
925 examples [00:02, 382.56 examples/s]
965 examples [00:02, 381.39 examples/s]
1004 examples [00:02, 364.08 examples/s]
1045 examples [00:03, 374.97 examples/s]
1083 examples [00:03, 373.90 examples/s]
1121 examples [00:03, 362.67 examples/s]
1159 examples [00:03, 365.57 examples/s]
1196 examples [00:03, 361.10 examples/s]
1234 examples [00:03, 365.86 examples/s]
1274 examples [00:03, 375.09 examples/s]
1312 examples [00:03, 376.34 examples/s]
1350 examples [00:03, 359.16 examples/s]
1390 examples [00:03, 368.66 examples/s]
1428 examples [00:04, 363.82 examples/s]
1467 examples [00:04, 370.62 examples/s]
1505 examples [00:04, 372.16 examples/s]
1543 examples [00:04, 361.77 examples/s]
1580 examples [00:04, 358.13 examples/s]
1622 examples [00:04, 372.81 examples/s]
1660 examples [00:04, 370.07 examples/s]
1698 examples [00:04, 370.10 examples/s]
1736 examples [00:04, 370.49 examples/s]
1774 examples [00:05, 371.09 examples/s]
1812 examples [00:05, 372.83 examples/s]
1850 examples [00:05, 368.93 examples/s]
1887 examples [00:05, 359.57 examples/s]
1926 examples [00:05, 366.09 examples/s]
1963 examples [00:05, 358.21 examples/s]
1999 examples [00:05, 353.47 examples/s]
2036 examples [00:05, 357.96 examples/s]
2074 examples [00:05, 363.98 examples/s]
2112 examples [00:05, 366.67 examples/s]
2151 examples [00:06, 371.61 examples/s]
2189 examples [00:06, 369.31 examples/s]
2231 examples [00:06, 382.34 examples/s]
2273 examples [00:06, 392.88 examples/s]
2313 examples [00:06, 384.37 examples/s]
2352 examples [00:06, 371.42 examples/s]
2390 examples [00:06, 365.77 examples/s]
2432 examples [00:06, 377.67 examples/s]
2470 examples [00:06, 367.36 examples/s]
2510 examples [00:06, 374.28 examples/s]
2548 examples [00:07, 374.68 examples/s]
2586 examples [00:07, 373.15 examples/s]
2624 examples [00:07, 374.26 examples/s]
2665 examples [00:07, 381.22 examples/s]
2704 examples [00:07, 373.76 examples/s]
2743 examples [00:07, 377.50 examples/s]
2781 examples [00:07, 373.68 examples/s]
2819 examples [00:07, 365.50 examples/s]
2862 examples [00:07, 380.24 examples/s]
2903 examples [00:08, 388.29 examples/s]
2943 examples [00:08, 387.85 examples/s]
2986 examples [00:08, 397.62 examples/s]
3026 examples [00:08, 389.43 examples/s]
3066 examples [00:08, 381.52 examples/s]
3105 examples [00:08, 368.40 examples/s]
3143 examples [00:08, 369.83 examples/s]
3184 examples [00:08, 378.81 examples/s]
3223 examples [00:08, 380.38 examples/s]
3262 examples [00:08, 374.00 examples/s]
3301 examples [00:09, 377.48 examples/s]
3339 examples [00:09, 375.95 examples/s]
3377 examples [00:09, 374.35 examples/s]
3417 examples [00:09, 378.62 examples/s]
3457 examples [00:09, 381.99 examples/s]
3496 examples [00:09, 373.23 examples/s]
3535 examples [00:09, 377.58 examples/s]
3575 examples [00:09, 381.88 examples/s]
3614 examples [00:09, 381.86 examples/s]
3653 examples [00:10, 368.35 examples/s]
3694 examples [00:10, 376.94 examples/s]
3732 examples [00:10, 372.39 examples/s]
3770 examples [00:10, 369.12 examples/s]
3812 examples [00:10, 382.21 examples/s]
3853 examples [00:10, 389.00 examples/s]
3893 examples [00:10, 367.17 examples/s]
3933 examples [00:10, 374.94 examples/s]
3973 examples [00:10, 381.56 examples/s]
4012 examples [00:10, 381.19 examples/s]
4052 examples [00:11, 385.06 examples/s]
4091 examples [00:11, 380.41 examples/s]
4130 examples [00:11, 366.98 examples/s]
4167 examples [00:11, 360.21 examples/s]
4208 examples [00:11, 371.40 examples/s]
4246 examples [00:11, 359.72 examples/s]
4283 examples [00:11, 358.09 examples/s]
4319 examples [00:11, 355.50 examples/s]
4357 examples [00:11, 362.25 examples/s]
4398 examples [00:12, 373.19 examples/s]
4440 examples [00:12, 383.20 examples/s]
4479 examples [00:12, 374.37 examples/s]
4518 examples [00:12, 376.61 examples/s]
4556 examples [00:12, 369.29 examples/s]
4594 examples [00:12, 362.45 examples/s]
4635 examples [00:12, 374.74 examples/s]
4674 examples [00:12, 377.44 examples/s]
4712 examples [00:12, 374.39 examples/s]
4751 examples [00:12, 377.24 examples/s]
4795 examples [00:13, 392.83 examples/s]
4835 examples [00:13, 388.06 examples/s]
4877 examples [00:13, 395.98 examples/s]
4917 examples [00:13, 390.05 examples/s]
4958 examples [00:13, 392.43 examples/s]
4998 examples [00:13, 382.61 examples/s]
5037 examples [00:13, 375.27 examples/s]
5075 examples [00:13, 371.98 examples/s]
5113 examples [00:13, 365.19 examples/s]
5150 examples [00:14, 366.31 examples/s]
5188 examples [00:14, 368.03 examples/s]
5231 examples [00:14, 384.50 examples/s]
5274 examples [00:14, 397.08 examples/s]
5314 examples [00:14, 393.65 examples/s]
5355 examples [00:14, 398.07 examples/s]
5395 examples [00:14, 383.03 examples/s]
5434 examples [00:14, 373.52 examples/s]
5472 examples [00:14, 352.05 examples/s]
5513 examples [00:14, 366.03 examples/s]
5558 examples [00:15, 386.04 examples/s]
5598 examples [00:15, 376.59 examples/s]
5637 examples [00:15, 376.85 examples/s]
5681 examples [00:15, 392.37 examples/s]
5721 examples [00:15, 385.21 examples/s]
5764 examples [00:15, 395.67 examples/s]
5804 examples [00:15, 391.42 examples/s]
5844 examples [00:15, 387.19 examples/s]
5883 examples [00:15, 385.30 examples/s]
5922 examples [00:16, 382.55 examples/s]
5961 examples [00:16, 383.40 examples/s]
6001 examples [00:16, 387.48 examples/s]
6040 examples [00:16, 385.39 examples/s]
6079 examples [00:16, 383.34 examples/s]
6122 examples [00:16, 395.32 examples/s]
Computing statistics...:  33% 1/3 [00:17<00:34, 17.38s/ split]I1020 19:50:20.760915 140610746677120 dataset_builder.py:458] Constructing tf.data.Dataset for split train, from /root/tensorflow_datasets/oxford_flowers102/2.0.0.incomplete37LVX4

0 examples [00:00, ? examples/s]
14 examples [00:00, 136.02 examples/s]
52 examples [00:00, 168.46 examples/s]
87 examples [00:00, 199.17 examples/s]
122 examples [00:00, 228.66 examples/s]
159 examples [00:00, 257.18 examples/s]
192 examples [00:00, 273.30 examples/s]
229 examples [00:00, 295.01 examples/s]
266 examples [00:00, 312.83 examples/s]
309 examples [00:00, 340.53 examples/s]
345 examples [00:01, 345.70 examples/s]
381 examples [00:01, 349.48 examples/s]
420 examples [00:01, 359.82 examples/s]
457 examples [00:01, 351.90 examples/s]
497 examples [00:01, 363.33 examples/s]
535 examples [00:01, 367.55 examples/s]
573 examples [00:01, 360.72 examples/s]
610 examples [00:01, 355.98 examples/s]
648 examples [00:01, 361.15 examples/s]
686 examples [00:01, 364.37 examples/s]
724 examples [00:02, 368.59 examples/s]
763 examples [00:02, 372.14 examples/s]
802 examples [00:02, 376.53 examples/s]
840 examples [00:02, 361.56 examples/s]
881 examples [00:02, 373.71 examples/s]
919 examples [00:02, 370.06 examples/s]
958 examples [00:02, 375.79 examples/s]
996 examples [00:02, 372.84 examples/s]
Computing statistics...:  67% 2/3 [00:20<00:13, 13.04s/ split]I1020 19:50:23.682512 140610746677120 dataset_builder.py:458] Constructing tf.data.Dataset for split validation, from /root/tensorflow_datasets/oxford_flowers102/2.0.0.incomplete37LVX4

0 examples [00:00, ? examples/s]
14 examples [00:00, 137.93 examples/s]
53 examples [00:00, 170.83 examples/s]
90 examples [00:00, 203.12 examples/s]
124 examples [00:00, 230.95 examples/s]
163 examples [00:00, 262.29 examples/s]
204 examples [00:00, 293.15 examples/s]
246 examples [00:00, 320.25 examples/s]
283 examples [00:00, 331.87 examples/s]
319 examples [00:00, 336.86 examples/s]
355 examples [00:01, 338.85 examples/s]
391 examples [00:01, 343.64 examples/s]
427 examples [00:01, 339.92 examples/s]
467 examples [00:01, 354.22 examples/s]
503 examples [00:01, 345.28 examples/s]
539 examples [00:01, 346.74 examples/s]
575 examples [00:01, 349.31 examples/s]
614 examples [00:01, 359.71 examples/s]
654 examples [00:01, 367.95 examples/s]
692 examples [00:01, 369.95 examples/s]
730 examples [00:02, 369.38 examples/s]
768 examples [00:02, 360.32 examples/s]
805 examples [00:02, 352.16 examples/s]
844 examples [00:02, 359.57 examples/s]
882 examples [00:02, 364.77 examples/s]
919 examples [00:02, 366.32 examples/s]
956 examples [00:02, 356.01 examples/s]
994 examples [00:02, 360.64 examples/s]
Computing statistics...: 100% 3/3 [00:23<00:00,  7.74s/ split]
Dataset oxford_flowers102 downloaded and prepared to /root/tensorflow_datasets/oxford_flowers102/2.0.0. Subsequent calls will reuse this data.
name: "oxford_flowers102"
description: "\nThe Oxford Flowers 102 dataset is a consistent of 102 flower categories commonly occurring\nin the United Kingdom. Each class consists of between 40 and 258 images. The images have\nlarge scale, pose and light variations. In addition, there are categories that have large\nvariations within the category and several very similar categories.\n\nThe dataset is divided into a training set, a validation set and a test set.\nThe training set and validation set each consist of 10 images per class (totalling 1020 images each).\nThe test set consists of the remaining 6149 images (minimum 20 per class).\n"
citation: "@InProceedings{Nilsback08,\n   author = \"Nilsback, M-E. and Zisserman, A.\",\n   title = \"Automated Flower Classification over a Large Number of Classes\",\n   booktitle = \"Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing\",\n   year = \"2008\",\n   month = \"Dec\"\n}\n"
size_in_bytes: 353121411
location {
  urls: "https://www.robots.ox.ac.uk/~vgg/data/flowers/102/"
}
schema {
  feature {
    name: "file_name"
    type: BYTES
  }
  feature {
    name: "image"
    type: INT
    shape {
      dim {
        size: -1
      }
      dim {
        size: -1
      }
      dim {
        size: 3
      }
    }
  }
  feature {
    name: "label"
    type: INT
  }
}
splits {
  name: "test"
  num_shards: 1
  statistics {
    num_examples: 6149
    features {
      name: "file_name"
      type: BYTES
      bytes_stats {
        common_stats {
          num_non_missing: 6149
        }
      }
    }
    features {
      name: "image"
      num_stats {
        common_stats {
          num_non_missing: 6149
        }
        max: 255.0
      }
    }
    features {
      name: "label"
      num_stats {
        common_stats {
          num_non_missing: 6149
        }
        max: 101.0
      }
    }
  }
  shard_lengths: 3074
  shard_lengths: 3075
  num_bytes: 260784877
}
splits {
  name: "train"
  num_shards: 1
  statistics {
    num_examples: 1020
    features {
      name: "file_name"
      type: BYTES
      bytes_stats {
        common_stats {
          num_non_missing: 1020
        }
      }
    }
    features {
      name: "image"
      num_stats {
        common_stats {
          num_non_missing: 1020
        }
        max: 255.0
      }
    }
    features {
      name: "label"
      num_stats {
        common_stats {
          num_non_missing: 1020
        }
        max: 101.0
      }
    }
  }
  shard_lengths: 1020
  num_bytes: 43474584
}
splits {
  name: "validation"
  num_shards: 1
  statistics {
    num_examples: 1020
    features {
      name: "file_name"
      type: BYTES
      bytes_stats {
        common_stats {
          num_non_missing: 1020
        }
      }
    }
    features {
      name: "image"
      num_stats {
        common_stats {
          num_non_missing: 1020
        }
        max: 255.0
      }
    }
    features {
      name: "label"
      num_stats {
        common_stats {
          num_non_missing: 1020
        }
        max: 101.0
      }
    }
  }
  shard_lengths: 1020
  num_bytes: 43180278
}
supervised_keys {
  input: "image"
  output: "label"
}
version: "2.0.0"
download_size: 344878000

Explore the Dataset

In [8]:
# TODO: Get the number of examples in each set from the dataset info.
total_examples = dataset_info.splits['train'].num_examples + dataset_info.splits['test'].num_examples

num_training_examples = dataset_info.splits['train'].num_examples
num_validation_examples = dataset_info.splits['validation'].num_examples
num_test_examples = dataset_info.splits['test'].num_examples


print('\t\u2022 There are {:,} examples in the training set'.format(num_training_examples))
print('\t\u2022 There are {:,} examples in the validation set'.format(num_validation_examples))
print('\t\u2022 There are {:,} examples in the test set'.format(num_test_examples))
# TODO: Get the number of classes in the dataset from the dataset info.
print('\t\u2022 There are {:,} classes in our dataset'.format(dataset_info.features['label'].num_classes))
	• There are 1,020 examples in the training set
	• There are 1,020 examples in the validation set
	• There are 6,149 examples in the test set
	• There are 102 classes in our dataset
In [9]:
# TODO: Print the shape and corresponding label of 3 images in the training set.
for image, label in training_set.take(3):
    image = image.numpy().squeeze()
    label = label.numpy()

    plt.imshow(image, cmap= plt.cm.binary)
    plt.colorbar()
    plt.show()

    print('\t\u2022 The shape of this image is:', image.shape)
    print('\t\u2022 The label of this image is:', label)
	• The shape of this image is: (500, 667, 3)
	• The label of this image is: 72
	• The shape of this image is: (500, 666, 3)
	• The label of this image is: 84
	• The shape of this image is: (670, 500, 3)
	• The label of this image is: 70
In [10]:
# TODO: Plot 1 image from the training set. 
for image, label in training_set.take(1):
    image = image.numpy().squeeze()
    label = label.numpy()
# Set the title of the plot to the corresponding image label. 
plt.imshow(image, cmap= plt.cm.binary)
plt.colorbar()
plt.title(label)
plt.show()

Label Mapping

You'll also need to load in a mapping from label to category name. You can find this in the file label_map.json. It's a JSON object which you can read in with the json module. This will give you a dictionary mapping the integer coded labels to the actual names of the flowers.

In [11]:
with open('label_map.json', 'r') as f:
    class_names = json.load(f)
print(json.dumps(class_names, indent=4))
{
    "21": "fire lily",
    "3": "canterbury bells",
    "45": "bolero deep blue",
    "1": "pink primrose",
    "34": "mexican aster",
    "27": "prince of wales feathers",
    "7": "moon orchid",
    "16": "globe-flower",
    "25": "grape hyacinth",
    "26": "corn poppy",
    "79": "toad lily",
    "39": "siam tulip",
    "24": "red ginger",
    "67": "spring crocus",
    "35": "alpine sea holly",
    "32": "garden phlox",
    "10": "globe thistle",
    "6": "tiger lily",
    "93": "ball moss",
    "33": "love in the mist",
    "9": "monkshood",
    "102": "blackberry lily",
    "14": "spear thistle",
    "19": "balloon flower",
    "100": "blanket flower",
    "13": "king protea",
    "49": "oxeye daisy",
    "15": "yellow iris",
    "61": "cautleya spicata",
    "31": "carnation",
    "64": "silverbush",
    "68": "bearded iris",
    "63": "black-eyed susan",
    "69": "windflower",
    "62": "japanese anemone",
    "20": "giant white arum lily",
    "38": "great masterwort",
    "4": "sweet pea",
    "86": "tree mallow",
    "101": "trumpet creeper",
    "42": "daffodil",
    "22": "pincushion flower",
    "2": "hard-leaved pocket orchid",
    "54": "sunflower",
    "66": "osteospermum",
    "70": "tree poppy",
    "85": "desert-rose",
    "99": "bromelia",
    "87": "magnolia",
    "5": "english marigold",
    "92": "bee balm",
    "28": "stemless gentian",
    "97": "mallow",
    "57": "gaura",
    "40": "lenten rose",
    "47": "marigold",
    "59": "orange dahlia",
    "48": "buttercup",
    "55": "pelargonium",
    "36": "ruby-lipped cattleya",
    "91": "hippeastrum",
    "29": "artichoke",
    "71": "gazania",
    "90": "canna lily",
    "18": "peruvian lily",
    "98": "mexican petunia",
    "8": "bird of paradise",
    "30": "sweet william",
    "17": "purple coneflower",
    "52": "wild pansy",
    "84": "columbine",
    "12": "colt's foot",
    "11": "snapdragon",
    "96": "camellia",
    "23": "fritillary",
    "50": "common dandelion",
    "44": "poinsettia",
    "53": "primula",
    "72": "azalea",
    "65": "californian poppy",
    "80": "anthurium",
    "76": "morning glory",
    "37": "cape flower",
    "56": "bishop of llandaff",
    "60": "pink-yellow dahlia",
    "82": "clematis",
    "58": "geranium",
    "75": "thorn apple",
    "41": "barbeton daisy",
    "95": "bougainvillea",
    "43": "sword lily",
    "83": "hibiscus",
    "78": "lotus lotus",
    "88": "cyclamen",
    "94": "foxglove",
    "81": "frangipani",
    "74": "rose",
    "89": "watercress",
    "73": "water lily",
    "46": "wallflower",
    "77": "passion flower",
    "51": "petunia"
}
In [12]:
# TODO: Plot 1 image from the training set. Set the title 
# of the plot to the corresponding class name. 
for image, label in training_set.take(1):
    image = image.numpy().squeeze()
    label = label.numpy()
plt.imshow(image, cmap= plt.cm.binary)
plt.colorbar()
plt.title(class_names[str(label)])
plt.show()

Create Pipeline

In [13]:
# TODO: Create a pipeline for each set.
batch_size = 32
image_size = 224


def format_image(image, label):
    image = tf.cast(image, tf.float32)
    image = tf.image.resize(image, (image_size, image_size))
    image /= 255
    return image, label


training_batches = training_set.shuffle(num_training_examples//4).map(format_image).batch(batch_size).prefetch(1)
validation_batches = validation_set.map(format_image).batch(batch_size).prefetch(1)
testing_batches = test_set.map(format_image).batch(batch_size).prefetch(1)

Build and Train the Classifier

Now that the data is ready, it's time to build and train the classifier. You should use the MobileNet pre-trained model from TensorFlow Hub to get the image features. Build and train a new feed-forward classifier using those features.

We're going to leave this part up to you. If you want to talk through it with someone, chat with your fellow students!

Refer to the rubric for guidance on successfully completing this section. Things you'll need to do:

  • Load the MobileNet pre-trained network from TensorFlow Hub.
  • Define a new, untrained feed-forward network as a classifier.
  • Train the classifier.
  • Plot the loss and accuracy values achieved during training for the training and validation set.
  • Save your trained model as a Keras model.

We've left a cell open for you below, but use as many as you need. Our advice is to break the problem up into smaller parts you can run separately. Check that each part is doing what you expect, then move on to the next. You'll likely find that as you work through each part, you'll need to go back and modify your previous code. This is totally normal!

When training make sure you're updating only the weights of the feed-forward network. You should be able to get the validation accuracy above 70% if you build everything right.

Note for Workspace users: One important tip if you're using the workspace to run your code: To avoid having your workspace disconnect during the long-running tasks in this notebook, please read in the earlier page in this lesson called Intro to GPU Workspaces about Keeping Your Session Active. You'll want to include code from the workspace_utils.py module. Also, If your model is over 1 GB when saved as a checkpoint, there might be issues with saving backups in your workspace. If your saved checkpoint is larger than 1 GB (you can open a terminal and check with ls -lh), you should reduce the size of your hidden layers and train again.

In [14]:
# TODO: Build and train your network.

URL = "https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4"
feature_extractor = hub.KerasLayer(URL, input_shape=(image_size, image_size,3))
feature_extractor.trainable = False

# Here we'll build
number_classes = dataset_info.features['label'].num_classes

model = tf.keras.Sequential([
        feature_extractor,
        tf.keras.layers.Dense(number_classes, activation = 'softmax')
])
model.summary()

# and compile our model as usual.
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# Let's see how the model performs on our test set
loss, accuracy = model.evaluate(testing_batches)
print('\nLoss on the TEST Set: {:,.3f}'.format(loss))
print('Accuracy on the TEST Set: {:.3%}'.format(accuracy))


# Now let's train our network 
EPOCHS = 6
history = model.fit(training_batches,
                    epochs = EPOCHS,
                    validation_data=validation_batches)
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
keras_layer (KerasLayer)     (None, 1280)              2257984   
_________________________________________________________________
dense (Dense)                (None, 102)               130662    
=================================================================
Total params: 2,388,646
Trainable params: 130,662
Non-trainable params: 2,257,984
_________________________________________________________________
193/193 [==============================] - 17s 90ms/step - loss: 5.1813 - accuracy: 0.0078

Loss on the TEST Set: 5.181
Accuracy on the TEST Set: 0.781%
Epoch 1/6
32/32 [==============================] - 6s 176ms/step - loss: 4.3561 - accuracy: 0.1088 - val_loss: 3.1503 - val_accuracy: 0.3578
Epoch 2/6
32/32 [==============================] - 6s 174ms/step - loss: 2.1161 - accuracy: 0.6765 - val_loss: 2.0131 - val_accuracy: 0.6598
Epoch 3/6
32/32 [==============================] - 6s 174ms/step - loss: 1.1012 - accuracy: 0.9039 - val_loss: 1.5301 - val_accuracy: 0.7363
Epoch 4/6
32/32 [==============================] - 6s 175ms/step - loss: 0.6692 - accuracy: 0.9510 - val_loss: 1.2891 - val_accuracy: 0.7667
Epoch 5/6
32/32 [==============================] - 6s 172ms/step - loss: 0.4446 - accuracy: 0.9882 - val_loss: 1.1498 - val_accuracy: 0.7853
Epoch 6/6
32/32 [==============================] - 5s 172ms/step - loss: 0.3146 - accuracy: 0.9931 - val_loss: 1.0554 - val_accuracy: 0.7902
In [15]:
# TODO: Plot the loss and accuracy values achieved during training for the training and validation set.

training_accuracy = history.history['accuracy']
validation_accuracy = history.history['val_accuracy']

training_loss = history.history['loss']
validation_loss = history.history['val_loss']

epochs_range=range(EPOCHS)

plt.figure(figsize=(8, 8))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, training_accuracy, label='Training Accuracy')
plt.plot(epochs_range, validation_accuracy, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, training_loss, label='Training Loss')
plt.plot(epochs_range, validation_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

Testing your Network

It's good practice to test your trained network on test data, images the network has never seen either in training or validation. This will give you a good estimate for the model's performance on completely new images. You should be able to reach around 70% accuracy on the test set if the model has been trained well.

In [16]:
# TODO: Print the loss and accuracy values achieved on the entire test set.

oss, accuracy = model.evaluate(testing_batches)

print('\t\u2022 Loss on the TEST Set: {:,.3f}'.format(loss))
print('\t\u2022 Accuracy on the TEST Set: {:.3%}'.format(accuracy))
193/193 [==============================] - 17s 90ms/step - loss: 1.2003 - accuracy: 0.7504
	• Loss on the TEST Set: 5.181
	• Accuracy on the TEST Set: 75.037%

Save the Model

Now that your network is trained, save the model so you can load it later for making inference. In the cell below save your model as a Keras model (i.e. save it as an HDF5 file).

In [17]:
# TODO: Save your trained model as a Keras model.
saved_path = './the_model.h5'
model.save(saved_path)

Load the Keras Model

Load the Keras model you saved above.

In [18]:
# TODO: Load the Keras model
reloaded_keras_model = tf.keras.models.load_model((saved_path),custom_objects={'KerasLayer':hub.KerasLayer})
reloaded_keras_model.summary()
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
keras_layer (KerasLayer)     (None, 1280)              2257984   
_________________________________________________________________
dense (Dense)                (None, 102)               130662    
=================================================================
Total params: 2,388,646
Trainable params: 130,662
Non-trainable params: 2,257,984
_________________________________________________________________

Inference for Classification

Now you'll write a function that uses your trained network for inference. Write a function called predict that takes an image, a model, and then returns the top $K$ most likely class labels along with the probabilities. The function call should look like:

probs, classes = predict(image_path, model, top_k)

If top_k=5 the output of the predict function should be something like this:

probs, classes = predict(image_path, model, 5)
print(probs)
print(classes)
> [ 0.01558163  0.01541934  0.01452626  0.01443549  0.01407339]
> ['70', '3', '45', '62', '55']

Your predict function should use PIL to load the image from the given image_path. You can use the Image.open function to load the images. The Image.open() function returns an Image object. You can convert this Image object to a NumPy array by using the np.asarray() function.

The predict function will also need to handle pre-processing the input image such that it can be used by your model. We recommend you write a separate function called process_image that performs the pre-processing. You can then call the process_image function from the predict function.

Image Pre-processing

The process_image function should take in an image (in the form of a NumPy array) and return an image in the form of a NumPy array with shape (224, 224, 3).

First, you should convert your image into a TensorFlow Tensor and then resize it to the appropriate size using tf.image.resize.

Second, the pixel values of the input images are typically encoded as integers in the range 0-255, but the model expects the pixel values to be floats in the range 0-1. Therefore, you'll also need to normalize the pixel values.

Finally, convert your image back to a NumPy array using the .numpy() method.

In [19]:
# TODO: Create the process_image function
def process_image(image):
    image = tf.convert_to_tensor(image, dtype=tf.float32)
    image = tf.image.resize(image, (image_size, image_size))
    image /= 255
    return image.numpy()

To check your process_image function we have provided 4 images in the ./test_images/ folder:

  • cautleya_spicata.jpg
  • hard-leaved_pocket_orchid.jpg
  • orange_dahlia.jpg
  • wild_pansy.jpg

The code below loads one of the above images using PIL and plots the original image alongside the image produced by your process_image function. If your process_image function works, the plotted image should be the correct size.

In [20]:
from PIL import Image

image_path = './test_images/hard-leaved_pocket_orchid.jpg'
im = Image.open(image_path)
test_image = np.asarray(im)

processed_test_image = process_image(test_image)

fig, (ax1, ax2) = plt.subplots(figsize=(10,10), ncols=2)
ax1.imshow(test_image)
ax1.set_title('Original Image')
ax2.imshow(processed_test_image)
ax2.set_title('Processed Image')
plt.tight_layout()
plt.show()

Once you can get images in the correct format, it's time to write the predict function for making inference with your model.

Inference

Remember, the predict function should take an image, a model, and then returns the top $K$ most likely class labels along with the probabilities. The function call should look like:

probs, classes = predict(image_path, model, top_k)

If top_k=5 the output of the predict function should be something like this:

probs, classes = predict(image_path, model, 5)
print(probs)
print(classes)
> [ 0.01558163  0.01541934  0.01452626  0.01443549  0.01407339]
> ['70', '3', '45', '62', '55']

Your predict function should use PIL to load the image from the given image_path. You can use the Image.open function to load the images. The Image.open() function returns an Image object. You can convert this Image object to a NumPy array by using the np.asarray() function.

Note: The image returned by the process_image function is a NumPy array with shape (224, 224, 3) but the model expects the input images to be of shape (1, 224, 224, 3). This extra dimension represents the batch size. We suggest you use the np.expand_dims() function to add the extra dimension.

In [21]:
# TODO: Create the predict function

def predict(image_path, model, K, cls_names = class_names):
    im = Image.open(image_path)
    pred_image = np.asarray(im)
    pred_image = process_image(pred_image)
    
    prediction = model.predict(np.expand_dims(pred_image, 0))

    pred_df = pd.DataFrame(prediction[0]).reset_index().rename(columns = {'index': 'class_code',0: 'prob'})\
                        .sort_values(by='prob', ascending = False).head(K).reset_index(drop=True)
    pred_df.loc[:,'class_code'] = pred_df.class_code + 1
    pred_df.loc[:,'class_name'] = np.nan

    for code in pred_df['class_code'].values:
        class_name = cls_names[str(code)]
        pred_df.loc[:,'class_name'] = np.where(pred_df.class_code == code, class_name, pred_df.class_name)
    
    return pred_df, pred_image

Sanity Check

It's always good to check the predictions made by your model to make sure they are correct. To check your predictions we have provided 4 images in the ./test_images/ folder:

  • cautleya_spicata.jpg
  • hard-leaved_pocket_orchid.jpg
  • orange_dahlia.jpg
  • wild_pansy.jpg

In the cell below use matplotlib to plot the input image alongside the probabilities for the top 5 classes predicted by your model. Plot the probabilities as a bar graph. The plot should look like this:

You can convert from the class integer labels to actual flower names using class_names.

In [22]:
# TODO: Plot the input image along with the top 5 classes

import glob

for x in glob.glob("./test_images/*.jpg"):
    if x.endswith('.jpg'):
        # extract the name
        name = x.split('/')[len(x.split('/'))-1][:-4]
        # apply predict function
        req = predict(x, model, 5)
        fig, (ax1, ax2) = plt.subplots(figsize=(10,5), ncols=2)
        ax1.imshow(req[1])
        ax1.set_title('input-image: {}'.format(name))
        ax2.barh(req[0].class_name, req[0].prob)
        ax2.set_title('predict-probability')
        plt.tight_layout()
        plt.show()
In [23]:
# to convert jupyter notebook html file
!jupyter nbconvert *.ipynb 
[NbConvertApp] WARNING | pattern u'*.ipynb' matched no files
This application is used to convert notebook files (*.ipynb) to various other
formats.

WARNING: THE COMMANDLINE INTERFACE MAY CHANGE IN FUTURE RELEASES.

Options
-------

Arguments that take values are actually convenience aliases to full
Configurables, whose aliases are listed on the help line. For more information
on full configurables, see '--help-all'.

--execute
    Execute the notebook prior to export.
--allow-errors
    Continue notebook execution even if one of the cells throws an error and include the error message in the cell output (the default behaviour is to abort conversion). This flag is only relevant if '--execute' was specified, too.
--no-input
    Exclude input cells and output prompts from converted document. 
    This mode is ideal for generating code-free reports.
--stdout
    Write notebook output to stdout instead of files.
--stdin
    read a single notebook file from stdin. Write the resulting notebook with default basename 'notebook.*'
--inplace
    Run nbconvert in place, overwriting the existing notebook (only 
    relevant when converting to notebook format)
-y
    Answer yes to any questions instead of prompting.
--clear-output
    Clear output of current file and save in place, 
    overwriting the existing notebook.
--debug
    set log level to logging.DEBUG (maximize logging output)
--no-prompt
    Exclude input and output prompts from converted document.
--generate-config
    generate default config file
--nbformat=<Enum> (NotebookExporter.nbformat_version)
    Default: 4
    Choices: [1, 2, 3, 4]
    The nbformat version to write. Use this to downgrade notebooks.
--output-dir=<Unicode> (FilesWriter.build_directory)
    Default: ''
    Directory to write output(s) to. Defaults to output to the directory of each
    notebook. To recover previous default behaviour (outputting to the current
    working directory) use . as the flag value.
--writer=<DottedObjectName> (NbConvertApp.writer_class)
    Default: 'FilesWriter'
    Writer class used to write the  results of the conversion
--log-level=<Enum> (Application.log_level)
    Default: 30
    Choices: (0, 10, 20, 30, 40, 50, 'DEBUG', 'INFO', 'WARN', 'ERROR', 'CRITICAL')
    Set the log level by value or name.
--reveal-prefix=<Unicode> (SlidesExporter.reveal_url_prefix)
    Default: u''
    The URL prefix for reveal.js (version 3.x). This defaults to the reveal CDN,
    but can be any url pointing to a copy  of reveal.js.
    For speaker notes to work, this must be a relative path to a local  copy of
    reveal.js: e.g., "reveal.js".
    If a relative path is given, it must be a subdirectory of the current
    directory (from which the server is run).
    See the usage documentation
    (https://nbconvert.readthedocs.io/en/latest/usage.html#reveal-js-html-
    slideshow) for more details.
--to=<Unicode> (NbConvertApp.export_format)
    Default: 'html'
    The export format to be used, either one of the built-in formats
    ['asciidoc', 'custom', 'html', 'latex', 'markdown', 'notebook', 'pdf',
    'python', 'rst', 'script', 'slides'] or a dotted object name that represents
    the import path for an `Exporter` class
--template=<Unicode> (TemplateExporter.template_file)
    Default: u''
    Name of the template file to use
--output=<Unicode> (NbConvertApp.output_base)
    Default: ''
    overwrite base name use for output files. can only be used when converting
    one notebook at a time.
--post=<DottedOrNone> (NbConvertApp.postprocessor_class)
    Default: u''
    PostProcessor class used to write the results of the conversion
--config=<Unicode> (JupyterApp.config_file)
    Default: u''
    Full path of a config file.

To see all available configurables, use `--help-all`

Examples
--------

    The simplest way to use nbconvert is
    
    > jupyter nbconvert mynotebook.ipynb
    
    which will convert mynotebook.ipynb to the default format (probably HTML).
    
    You can specify the export format with `--to`.
    Options include ['asciidoc', 'custom', 'html', 'latex', 'markdown', 'notebook', 'pdf', 'python', 'rst', 'script', 'slides'].
    
    > jupyter nbconvert --to latex mynotebook.ipynb
    
    Both HTML and LaTeX support multiple output templates. LaTeX includes
    'base', 'article' and 'report'.  HTML includes 'basic' and 'full'. You
    can specify the flavor of the format used.
    
    > jupyter nbconvert --to html --template basic mynotebook.ipynb
    
    You can also pipe the output to stdout, rather than a file
    
    > jupyter nbconvert mynotebook.ipynb --stdout
    
    PDF is generated via latex
    
    > jupyter nbconvert mynotebook.ipynb --to pdf
    
    You can get (and serve) a Reveal.js-powered slideshow
    
    > jupyter nbconvert myslides.ipynb --to slides --post serve
    
    Multiple notebooks can be given at the command line in a couple of 
    different ways:
    
    > jupyter nbconvert notebook*.ipynb
    > jupyter nbconvert notebook1.ipynb notebook2.ipynb
    
    or you can specify the notebooks list in a config file, containing::
    
        c.NbConvertApp.notebooks = ["my_notebook.ipynb"]
    
    > jupyter nbconvert --config mycfg.py